Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Kevin Wang

Kevin Wang

3 indexed papers

Recent (6 mo)
3
With code
0
Influential cites
0
Benchmarked
0

Publications per year

3
26

Top categories

AI×3Crypto×2ML×1

Frequent co-authors

Yang Yang1×
Yuanhai Luo1×
Hang Yin1×
Jie Cai1×
Shunfan Zhou1×
Wenfeng Wang1×

Research Timeline

2026
Kill-Chain Canaries: Stage-Level Tracking of Prompt Injection Across Attack Surfaces and Model Safety Tiers

The paper introduces a kill-chain canary methodology to diagnose prompt injection vulnerabilities across multi-stage LLM pipelines, revealing that write-node placement and document format are critical safety weak points.

MINDGAMES: A Live Arena for Evaluating Social and Strategic Reasoning in Multi-Agent LLMs

The paper introduces Mindgames, a comprehensive multi-game arena for evaluating LLM agents' sustained social and strategic reasoning, demonstrating that current evaluations are limited by structural scaffolding and error-survival confounds.

Implement Kubernetes Pod-Level Remote Attestation for Confidential Workloads on dstack

dstack-capsule is a Kubernetes platform that enables fine-grained, Pod-level remote attestation on Intel TDX, allowing multiple confidential workloads to share a single VM without sacrificing security or incurring excessive resource overhead.

Highlighted terms show continued research focus across papers

Papers

cs.CRcs.AIRecentJun 2, 2026

Implement Kubernetes Pod-Level Remote Attestation for Confidential Workloads on dstack

Yang Yang, Kevin Wang, Yuanhai Luo, Hang Yin +3 more

dstack-capsule is a Kubernetes platform that enables fine-grained, Pod-level remote attestation on Intel TDX, allowing multiple confidential workloads to share a single VM without sacrificing security…

View →
cs.AIRecentMay 28, 2026

MINDGAMES: A Live Arena for Evaluating Social and Strategic Reasoning in Multi-Agent LLMs

Kevin Wang, Anna Thöni, Benjamin Kempinski, Bobby Cheng +49 more

The paper introduces Mindgames, a comprehensive multi-game arena for evaluating LLM agents' sustained social and strategic reasoning, demonstrating that current evaluations are limited by structural s…

View →
cs.CRcs.AIcs.LGRecentMar 30, 2026

Kill-Chain Canaries: Stage-Level Tracking of Prompt Injection Across Attack Surfaces and Model Safety Tiers

Haochuan Kevin Wang, Zechen Zhang

The paper introduces a kill-chain canary methodology to diagnose prompt injection vulnerabilities across multi-stage LLM pipelines, revealing that write-node placement and document format are critical…

View →